Upload folder using huggingface_hub

checkpoint-1750/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

checkpoint-1750/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1d894ae4b9d5cc26ee8be188e69a18d10101e4dac56c66b2e2c54b9ea354e7c
+size 267847948

checkpoint-1750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1e3fb5918c9d4336aa7864deef0a4686ba6690f773e7171d90490ec93876f9
+size 535758010

checkpoint-1750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:978f7bab02af7657e390514650a4953fe69eab70770f065bdbb10941acb77c40
+size 14244

checkpoint-1750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ddfaf0c262bfe460a222956722661d67bbbdf55c68aa1429f43b600fd33ec0d
+size 1064

checkpoint-1750/trainer_state.json

@@ -0,0 +1,185 @@
+{
+  "best_metric": 0.9856031417621324,
+  "best_model_checkpoint": "distilbert-type-classifier/checkpoint-1750",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.4620862007141113,
+      "learning_rate": 1.923809523809524e-05,
+      "loss": 0.8914,
+      "step": 100
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.9015448093414307,
+      "learning_rate": 1.8476190476190478e-05,
+      "loss": 0.186,
+      "step": 200
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.17388969659805298,
+      "learning_rate": 1.7714285714285717e-05,
+      "loss": 0.0844,
+      "step": 300
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 5.441539764404297,
+      "learning_rate": 1.6952380952380955e-05,
+      "loss": 0.0738,
+      "step": 400
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07328463345766068,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.0524,
+      "step": 500
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.07699141651391983,
+      "learning_rate": 1.542857142857143e-05,
+      "loss": 0.0567,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.823246002197266,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.0444,
+      "step": 700
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.07251616567373276,
+      "learning_rate": 1.3904761904761905e-05,
+      "loss": 0.0375,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9849949983327776,
+      "eval_f1": 0.9845642879906822,
+      "eval_loss": 0.07195836305618286,
+      "eval_precision": 0.9850021393367597,
+      "eval_recall": 0.9849949983327776,
+      "eval_runtime": 11.3969,
+      "eval_samples_per_second": 263.142,
+      "eval_steps_per_second": 16.496,
+      "step": 875
+    },
+    {
+      "epoch": 1.0285714285714285,
+      "grad_norm": 0.15092064440250397,
+      "learning_rate": 1.3142857142857145e-05,
+      "loss": 0.0487,
+      "step": 900
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.019707441329956055,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.0295,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.019482087343931198,
+      "learning_rate": 1.1619047619047621e-05,
+      "loss": 0.019,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 0.017313998192548752,
+      "learning_rate": 1.0857142857142858e-05,
+      "loss": 0.0303,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4857142857142858,
+      "grad_norm": 0.02844456024467945,
+      "learning_rate": 1.0095238095238096e-05,
+      "loss": 0.0188,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.3132454454898834,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.0148,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.033423177897930145,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.0216,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 0.012587839737534523,
+      "learning_rate": 7.809523809523811e-06,
+      "loss": 0.0099,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.010759529657661915,
+      "learning_rate": 7.047619047619048e-06,
+      "loss": 0.0089,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9859953317772591,
+      "eval_f1": 0.9856031417621324,
+      "eval_loss": 0.06867047399282455,
+      "eval_precision": 0.9859730777105192,
+      "eval_recall": 0.9859953317772591,
+      "eval_runtime": 11.4007,
+      "eval_samples_per_second": 263.055,
+      "eval_steps_per_second": 16.49,
+      "step": 1750
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 927155754656256.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609d9e093ff10cb72ff2ceab0b60b959ffb5a8e69641d5f5afc035f09f45f51b
+size 5304

checkpoint-2625/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

checkpoint-2625/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f122579f057d33dc7f447e9da1748ae33d185fe72c716a49c6d7a9d7edb170f
+size 267847948

checkpoint-2625/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efeb65ae52e78add1ec6957140de6b43be8937777687cbab5141356e39975545
+size 535758010

checkpoint-2625/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08bb7394ebf849123be4226fab5ffe87e4adaf61e755aa694735f27486d7d221
+size 14244

checkpoint-2625/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84decddedc343afdfe65c5401b1ea8f21003cfa643ae145ae2bd45c9f7512652
+size 1064

checkpoint-2625/trainer_state.json

@@ -0,0 +1,260 @@
+{
+  "best_metric": 0.9902624352671658,
+  "best_model_checkpoint": "distilbert-type-classifier/checkpoint-2625",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2625,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.4620862007141113,
+      "learning_rate": 1.923809523809524e-05,
+      "loss": 0.8914,
+      "step": 100
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.9015448093414307,
+      "learning_rate": 1.8476190476190478e-05,
+      "loss": 0.186,
+      "step": 200
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.17388969659805298,
+      "learning_rate": 1.7714285714285717e-05,
+      "loss": 0.0844,
+      "step": 300
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 5.441539764404297,
+      "learning_rate": 1.6952380952380955e-05,
+      "loss": 0.0738,
+      "step": 400
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07328463345766068,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.0524,
+      "step": 500
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.07699141651391983,
+      "learning_rate": 1.542857142857143e-05,
+      "loss": 0.0567,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.823246002197266,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.0444,
+      "step": 700
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.07251616567373276,
+      "learning_rate": 1.3904761904761905e-05,
+      "loss": 0.0375,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9849949983327776,
+      "eval_f1": 0.9845642879906822,
+      "eval_loss": 0.07195836305618286,
+      "eval_precision": 0.9850021393367597,
+      "eval_recall": 0.9849949983327776,
+      "eval_runtime": 11.3969,
+      "eval_samples_per_second": 263.142,
+      "eval_steps_per_second": 16.496,
+      "step": 875
+    },
+    {
+      "epoch": 1.0285714285714285,
+      "grad_norm": 0.15092064440250397,
+      "learning_rate": 1.3142857142857145e-05,
+      "loss": 0.0487,
+      "step": 900
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.019707441329956055,
+      "learning_rate": 1.2380952380952383e-05,
+      "loss": 0.0295,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2571428571428571,
+      "grad_norm": 0.019482087343931198,
+      "learning_rate": 1.1619047619047621e-05,
+      "loss": 0.019,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3714285714285714,
+      "grad_norm": 0.017313998192548752,
+      "learning_rate": 1.0857142857142858e-05,
+      "loss": 0.0303,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4857142857142858,
+      "grad_norm": 0.02844456024467945,
+      "learning_rate": 1.0095238095238096e-05,
+      "loss": 0.0188,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.3132454454898834,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 0.0148,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.033423177897930145,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.0216,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8285714285714287,
+      "grad_norm": 0.012587839737534523,
+      "learning_rate": 7.809523809523811e-06,
+      "loss": 0.0099,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9428571428571428,
+      "grad_norm": 0.010759529657661915,
+      "learning_rate": 7.047619047619048e-06,
+      "loss": 0.0089,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9859953317772591,
+      "eval_f1": 0.9856031417621324,
+      "eval_loss": 0.06867047399282455,
+      "eval_precision": 0.9859730777105192,
+      "eval_recall": 0.9859953317772591,
+      "eval_runtime": 11.4007,
+      "eval_samples_per_second": 263.055,
+      "eval_steps_per_second": 16.49,
+      "step": 1750
+    },
+    {
+      "epoch": 2.057142857142857,
+      "grad_norm": 0.021305246278643608,
+      "learning_rate": 6.285714285714286e-06,
+      "loss": 0.0126,
+      "step": 1800
+    },
+    {
+      "epoch": 2.1714285714285713,
+      "grad_norm": 0.012538880109786987,
+      "learning_rate": 5.523809523809525e-06,
+      "loss": 0.007,
+      "step": 1900
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": 0.009147515520453453,
+      "learning_rate": 4.761904761904762e-06,
+      "loss": 0.0108,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.053507789969444275,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0009,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5142857142857142,
+      "grad_norm": 0.02192852832376957,
+      "learning_rate": 3.2380952380952385e-06,
+      "loss": 0.0025,
+      "step": 2200
+    },
+    {
+      "epoch": 2.6285714285714286,
+      "grad_norm": 5.773326396942139,
+      "learning_rate": 2.4761904761904764e-06,
+      "loss": 0.0092,
+      "step": 2300
+    },
+    {
+      "epoch": 2.742857142857143,
+      "grad_norm": 0.007939064875245094,
+      "learning_rate": 1.7142857142857145e-06,
+      "loss": 0.0007,
+      "step": 2400
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.008160616271197796,
+      "learning_rate": 9.523809523809525e-07,
+      "loss": 0.0044,
+      "step": 2500
+    },
+    {
+      "epoch": 2.9714285714285715,
+      "grad_norm": 0.009465965442359447,
+      "learning_rate": 1.904761904761905e-07,
+      "loss": 0.0085,
+      "step": 2600
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9903301100366789,
+      "eval_f1": 0.9902624352671658,
+      "eval_loss": 0.05811132863163948,
+      "eval_precision": 0.9902595291145613,
+      "eval_recall": 0.9903301100366789,
+      "eval_runtime": 11.257,
+      "eval_samples_per_second": 266.413,
+      "eval_steps_per_second": 16.701,
+      "step": 2625
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1390733631984384.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2625/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609d9e093ff10cb72ff2ceab0b60b959ffb5a8e69641d5f5afc035f09f45f51b
+size 5304

checkpoint-875/config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

checkpoint-875/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ba872f979cf3b152ea5b9aecf016cfd0d69ae35545b63ba7eb4c7b9ac2fc8c
+size 267847948

checkpoint-875/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4a1538cc2e2669793b1fe565f860f8e377be35a7a70bb012c2a4d3c4ec1d09
+size 535758010

checkpoint-875/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec995f4ba70e374efef67b4a374fa81d531514c9ed99243e50bd5409be012bef
+size 14244

checkpoint-875/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e0f293fb265866b04cf2e58f1795f83a3571bad9174a30158203f83d1c29522
+size 1064

checkpoint-875/trainer_state.json

@@ -0,0 +1,110 @@
+{
+  "best_metric": 0.9845642879906822,
+  "best_model_checkpoint": "distilbert-type-classifier/checkpoint-875",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 1.4620862007141113,
+      "learning_rate": 1.923809523809524e-05,
+      "loss": 0.8914,
+      "step": 100
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 0.9015448093414307,
+      "learning_rate": 1.8476190476190478e-05,
+      "loss": 0.186,
+      "step": 200
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.17388969659805298,
+      "learning_rate": 1.7714285714285717e-05,
+      "loss": 0.0844,
+      "step": 300
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 5.441539764404297,
+      "learning_rate": 1.6952380952380955e-05,
+      "loss": 0.0738,
+      "step": 400
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.07328463345766068,
+      "learning_rate": 1.6190476190476193e-05,
+      "loss": 0.0524,
+      "step": 500
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 0.07699141651391983,
+      "learning_rate": 1.542857142857143e-05,
+      "loss": 0.0567,
+      "step": 600
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 13.823246002197266,
+      "learning_rate": 1.4666666666666666e-05,
+      "loss": 0.0444,
+      "step": 700
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.07251616567373276,
+      "learning_rate": 1.3904761904761905e-05,
+      "loss": 0.0375,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.9849949983327776,
+      "eval_f1": 0.9845642879906822,
+      "eval_loss": 0.07195836305618286,
+      "eval_precision": 0.9850021393367597,
+      "eval_recall": 0.9849949983327776,
+      "eval_runtime": 11.3969,
+      "eval_samples_per_second": 263.142,
+      "eval_steps_per_second": 16.496,
+      "step": 875
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2625,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 463577877328128.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-875/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609d9e093ff10cb72ff2ceab0b60b959ffb5a8e69641d5f5afc035f09f45f51b
+size 5304

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 30522
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f122579f057d33dc7f447e9da1748ae33d185fe72c716a49c6d7a9d7edb170f
+size 267847948

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:609d9e093ff10cb72ff2ceab0b60b959ffb5a8e69641d5f5afc035f09f45f51b
+size 5304

type_mapping.json

@@ -0,0 +1 @@
+{"0": "coherent", "1": "grammatical_errors", "2": "random_bytes", "3": "random_tokens", "4": "random_words", "5": "run_on", "6": "word_soup"}